| { | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2DoubleHeadsModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "do_sample": false, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "eos_token_ids": 0, | |
| "finetuning_task": "swag", | |
| "hidden_dropout_prob": 0.1, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_epsilon": 1e-05, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_layer": 12, | |
| "n_positions": 1024, | |
| "num_beams": 1, | |
| "num_labels": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "pruned_heads": {}, | |
| "repetition_penalty": 1.0, | |
| "resid_pdrop": 0.1, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "use_bfloat16": false, | |
| "vocab_size": 50257 | |
| } | |